M
MCP Directory CURATED DIRECTORY
911 MCP servers indexed
中文
← Back to directory
COMPARE UP TO 4 SERVERS

Compare MCP servers

Compare scores, permissions, risks, and fit in one decision-focused table.

DimensionUnity MCP Server330+ tools to turn Claude into a full Unity Editor & Hub copilotMartinLoop MCP ServerAn independent control layer that gives AI coding agents budgets, brakes, and receipts
FMRS50 / 100 · D79 / 100 · B
Reliability4 / 2012 / 20
Security and permissions6 / 2018 / 20
Maintenance12 / 2016 / 20
Documentation15 / 2018 / 20
Setup experience13 / 2015 / 20
Best for
  • Independent developers and small studios looking for a free, open-source solution to control Unity with AI
  • Developers who want to automate game development workflows using MCP-compatible clients like Claude or Cursor
  • Teams needing an extensive toolset covering a broad range of Unity features
  • Engineering teams scaling AI coding agents while controlling spend
  • Platform teams that need auditable, rollback-aware agent execution records
  • Organizations using multiple agents (Claude, Codex, Gemini) under one governed flow
Not for
  • Professional game companies requiring commercial support or enterprise guarantees
  • Beginners who are not comfortable with environment configuration or command-line tools (requires Node.js 18+ and Unity Hub)
  • Users who want to use Unity's native AI features within Unity 6.2+ without external MCP clients
  • Developers who just want a simple code-completion helper without run governance
  • Teams unwilling to accept local JSONL run records with HMAC signing
  • Environments without a supported adapter (Claude/Codex/Gemini CLIs, direct provider, or verifier-only)
Required permissions
  • Read/modify Unity project files, create/delete assets and scripts
  • Execute Unity Editor commands, read console and compilation logs
  • Control Unity Hub (list/install editors) requiring UNITY_HUB_PATH environment variable
  • Communicate with the Unity Editor over HTTP bridge, default port 7890
  • Read/write access to the configured repo root (writable scope restrictable via --allow-path/--deny-path)
  • Ability to invoke the chosen agent CLI (Claude/Codex/Gemini, etc.) and its underlying model account
  • Local disk writes for run records, receipts, and share outputs (share/run-receipt., etc.)
  • Execution of user-configured verifier commands (e.g. npm test)
Risks and side effects
  • Data loss risk due to automatic creation/deletion of assets and scripts; recommend regular project backups
  • AI-generated code may introduce errors or corrupt the project
  • Misconfiguration of environment variables (e.g., UNITY_HUB_PATH) can cause connection failures
  • Using a non-standard license (AnkleBreaker Open License) might restrict commercial redistribution
  • Verifier commands are executed; poorly chosen verifier commands carry security risk despite preflight policy checks
  • Cost and token figures may be estimates (labeled with provenance) and should not be treated as settled accounting
  • Receipt integrity must be verified before use as trustworthy evidence; missing rollback evidence is flagged as EVIDENCE_BOUNDARY
  • Policy defaults come from martin.config.yaml and can be overridden by CLI flags; misconfiguration can loosen safety boundaries
Supported clientsClaude DesktopClaude Code, Codex, Gemini CLI, Cursor, VS Code, GitHub Copilot, Continue
Tools00